| Upload Date | January 29 2026 08:51 AM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 26.2.1 |
| Model | iPad Pro (12.9-inch 5th generation) |
| Model ID | iPad13,8 |
| Motherboard | J522AP |
| CPU Information | |
|---|---|
| Name | Apple M1 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.19 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.34 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1302
242.1 IPS |
|
|
Image Classification (HP)
|
100% |
6220
1.16 KIPS |
|
|
Image Classification (Q)
|
96% |
5558
1.04 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1312
21.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
9052
146.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
9106
147.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
6009
7.01 IPS |
|
|
Pose Estimation (HP)
|
100% |
67227
78.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
64548
75.7 IPS |
|
|
Object Detection (SP)
|
100% |
1380
109.5 IPS |
|
|
Object Detection (HP)
|
99% |
6543
520.5 IPS |
|
|
Object Detection (Q)
|
91% |
6194
494.9 IPS |
|
|
Face Detection (SP)
|
100% |
2968
35.3 IPS |
|
|
Face Detection (HP)
|
100% |
12510
148.6 IPS |
|
|
Face Detection (Q)
|
100% |
11682
138.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
5467
42.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
42689
328.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
42440
331.7 IPS |
|
|
Style Transfer (SP)
|
100% |
16506
21.2 IPS |
|
|
Style Transfer (HP)
|
100% |
119274
153.3 IPS |
|
|
Style Transfer (Q)
|
96% |
112348
145.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3456
127.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
22811
842.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
22516
831.4 IPS |
|
|
Text Classification (SP)
|
100% |
2378
3.17 KIPS |
|
|
Text Classification (HP)
|
99% |
4174
5.57 KIPS |
|
|
Text Classification (Q)
|
93% |
4149
5.57 KIPS |
|
|
Machine Translation (SP)
|
100% |
2465
42.5 IPS |
|
|
Machine Translation (HP)
|
100% |
2480
42.7 IPS |
|
|
Machine Translation (Q)
|
98% |
2542
43.9 IPS |